Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 5086 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.2750. Min Range: -1.2750

Max Act: 1.1027. Min Act: -0.0000

Data Index: 1405962 (Python Code)

Max Activating Token Index: 882

Text #1

Max Range: 1.2750. Min Range: -1.2750

Max Act: 1.2750. Min Act: -0.0000

Data Index: 1424467 (Python Code)

Max Activating Token Index: 104

Text #2

Max Range: 1.2750. Min Range: -1.2750

Max Act: 0.9719. Min Act: -0.0000

Data Index: 1383668 (Python Code)

Max Activating Token Index: 293

Text #3

Max Range: 1.2750. Min Range: -1.2750

Max Act: 0.8957. Min Act: -0.0000

Data Index: 1465659 (Python Code)

Max Activating Token Index: 675

Text #4

Max Range: 1.2750. Min Range: -1.2750

Max Act: 0.8582. Min Act: -0.0000

Data Index: 1366382 (Python Code)

Max Activating Token Index: 323

Text #5

Max Range: 1.2750. Min Range: -1.2750

Max Act: 0.8497. Min Act: -0.0000

Data Index: 1648474 (Python Code)

Max Activating Token Index: 248

Text #6

Max Range: 1.2750. Min Range: -1.2750

Max Act: 0.8504. Min Act: -0.0000

Data Index: 1558195 (Python Code)

Max Activating Token Index: 149

Text #7

Max Range: 1.2750. Min Range: -1.2750

Max Act: 0.8848. Min Act: -0.0000

Data Index: 1647937 (Python Code)

Max Activating Token Index: 444

Text #8

Max Range: 1.2750. Min Range: -1.2750

Max Act: 0.7960. Min Act: -0.0000

Data Index: 1506010 (Python Code)

Max Activating Token Index: 142

Text #9

Max Range: 1.2750. Min Range: -1.2750

Max Act: 0.8374. Min Act: -0.0000

Data Index: 1378726 (Python Code)

Max Activating Token Index: 177

Text #10

Max Range: 1.2750. Min Range: -1.2750

Max Act: 0.7551. Min Act: -0.0000

Data Index: 1589459 (Python Code)

Max Activating Token Index: 710

Text #11

Max Range: 1.2750. Min Range: -1.2750

Max Act: 0.8130. Min Act: -0.0000

Data Index: 1494336 (Python Code)

Max Activating Token Index: 960

Text #12

Max Range: 1.2750. Min Range: -1.2750

Max Act: 0.7875. Min Act: -0.0000

Data Index: 1637422 (Python Code)

Max Activating Token Index: 747

Text #13

Max Range: 1.2750. Min Range: -1.2750

Max Act: 0.7395. Min Act: -0.0000

Data Index: 1402359 (Python Code)

Max Activating Token Index: 519

Text #14

Max Range: 1.2750. Min Range: -1.2750

Max Act: 0.7943. Min Act: -0.0000

Data Index: 1608141 (Python Code)

Max Activating Token Index: 166

Text #15

Max Range: 1.2750. Min Range: -1.2750

Max Act: 0.8243. Min Act: -0.0000

Data Index: 1495088 (Python Code)

Max Activating Token Index: 404

Text #16

Max Range: 1.2750. Min Range: -1.2750

Max Act: 0.6919. Min Act: -0.0000

Data Index: 1396432 (Python Code)

Max Activating Token Index: 890

Text #17

Max Range: 1.2750. Min Range: -1.2750

Max Act: 0.7076. Min Act: -0.0000

Data Index: 1489606 (Python Code)

Max Activating Token Index: 1003

Text #18

Max Range: 1.2750. Min Range: -1.2750

Max Act: 0.7255. Min Act: -0.0000

Data Index: 1537171 (Python Code)

Max Activating Token Index: 596

Text #19

Max Range: 1.2750. Min Range: -1.2750

Max Act: 0.7496. Min Act: -0.0000

Data Index: 1469900 (Python Code)

Max Activating Token Index: 432